Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover read-only, idempotent and open-world behavior, so the description's job is to add context — and it does: the underlying dataset (gov_10dd_edpt1, EDP notifications from April and October), annual-only granularity, provisional latest year, and a 1-credit cost. What it omits is any note on how aggregates like EU27_2020 or EA behave versus single countries.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The core definition and sign convention are front-loaded, followed by example intent, provenance, temporal caveats and cost in a tight sequence. Every clause carries information; the parenthetical cost note is the only element that could be trimmed.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description correctly supplies the one piece needed to interpret results — negative means deficit, expressed as a percentage of GDP. The dataset provenance and provisional-year warning round out the picture, leaving only minor gaps about aggregate/country coverage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with both `n` and `geo` fully documented in the schema itself, so the schema already does the heavy lifting. The description only adds the framing “one European country” and the deficit sign convention, which is useful but does not extend parameter meaning beyond the structured fields.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific metric (annual general government deficit/surplus as % of GDP), states the unit and the sign convention, and pins it to a named Eurostat dataset. It is clearly distinguishable from siblings such as eu_government_debt_ratio or eu_gdp_growth, though it never explicitly contrasts itself with them.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Two concrete example questions (“what is France's budget deficit”, “which countries break the 3% rule”) make the intended usage obvious, and the “annual only” constraint plus provisional-latest-year caveat define the boundary of valid use. It stops short of naming an alternative tool for quarterly or non-EU data.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.